Challenges and Visions of
Game Analytics
What Lies Beneath?
Definitions
 Analytics
 Game Analytics
 Game Telemetry
 Game Metrics
Analytics
 The process of discovering and communicating patterns in
data towards solving problems in business
 Supporting enterprise decision management
 Driving action
 Improving performance
 Or for purely frivolous and artistic reasons!
Game Analytics
 A specific domain of analytics: game development and game
research
 The game as a product: user experience, revenue …
 The game as a project: the process of developing the game
Game telemetry
 Quantitative, unprocessed data obtained over any distance,
which pertain to game development or game research.
 Describes attributes about objects
 Many sources: Installed clients, game servers, mobile units,
user testing/playtesting
Game metrics
 Interpretable, quantitative measure of one or more attributes
of one or more objects – operating in the context of games
 Object: virtual item, player, user, process, developer, forum
post ....
 Attribute: an aspect of the object
 Context: tied to process, performance or users of games.
1. Standards
 Lack of standards
 Makes it hard to communicate and share knowledge
 Need a ”game analytics association” – to develop
standards of terminology, practices and ethical guidelines
2. Unique beasts
 Games are not websites
 Goal of games: user experience – not selling running shoes
(virtual shoes maybe)
 Games can be immensely complex information systems
 100+ possible user/system and user/user interactions
 Extended periods of user-game interaction
 From 1 to lots of people interacting in-game
 Hard to directly import methods from other IT-fields –
adaptation needed
3. Social online focus
 Most advanced analytics currently in social online games/F2P
– and focused on monetization





A/B
Classification
Prediction
Segmentation
Etc.
 Rest of industry ”mostly” basic behavior analysis
 Need analytics to improve UX, not just sell Farm Potions +5
 Knowledge transfer image
4. Knowledge transfer
 What is going on?
 Minimal knowledge flow about methods, algorithms, ideas
 No dedicated conferences or workshops
 Presentations at events high level
 Not oriented towards application
 More high-level, marketing and ”bragging” than helping ...
4. Knowledge transfer
 Analytics is business intelligence – holds direct monetary
value
 A strong predictive algorithm can make a game
 Value: therefore kept confidential
 Problem: re-inventing the deep platter
 Need the front-runners to take charge: everybody benefits
from knowledge transfer
5. Knowledge gulf
 Knowledge gulf: academia – industry
 Academia provides a strong partner in analytics
 1000´s of specialists in dozens of fields
 Can do explorative/blue sky research
 Zynga, Wooga, Blizzard, EA ... – can build the expertise inhouse – what about small/medium devs? – collaborate to
innovate!
6. Lots´n lots of data
 Even a mid-size game can generate TBs of data per week –>
storage/processing
 Reporting needs to be fast -> rapid analysis
 Bandwidth vs. data coverage -> feature selection
 Coverage vs. speed -> sampling
"You are no longer an
individual, you are a data
cluster bound to a vast global
network" –
7. Unrivaled power
”Never before have so few
known so much
about so many”
Unrivaled power
2 powerful tools for monetization:
User knowledge
Analytics
Unrivaled power
 User knowledge
 In-game
 Purchasing
 From game platforms (Facebook etc.)
 From Net tracking (Google etc.)
 Clickstreams
 From mining the Net (social mining)
 Geodata (mobile phones)
 National person databases
 ...
 In the future knowledge of users will increase
Unrivaled power
 Analytics & user research
 Large-scale, data mining
 Prediction, clustering, etc.
 Behavioral Biology
 Behavioral Psychology
 Social/community behavior science
 When playing games, the barriers are down
Unrivaled power
User knowledge
Analytics
Great games
 Luke skywalker image
Unrivaled power
User knowledge
Analytics
Revenue requirement
(potential for) Great evil
 Darth vader image
Game data mining
Huge untapped potential in dozens of
fields/sectors:
 Human behavior analysis
 Spatial analytics
 Behavioral economics
 Insurance, banking and finance
 Social and community research
 Ecology and large-scale biological modeling
 ...
Game data mining
 3 high-potential areas of game data mining:
 Prediction: inform about future behavior of users
 Behavioral clustering: making high-dimensional behavior
datasets accessible
 Association and sequence: finding the patterns and
associations in how games are played
Behavioral clustering
SIVM: finding extreme profiles
 Assassins
 Veterans
 Target dummies
 Assault-Recon
 Medic-Engineer
 Driver
 Assault wannabee
Behavioral clustering
 Each different playstyles, and different things that
keep them in the game
 ”Driver”: drives, flies, sails – all the time and favors
maps with vehicles
 ”Assassin”: kills – afar or close – no vehicles
 ”Target dummies”: unskilled newbies
Behavioral clustering
 Use behavioral clustering to find profiles, then
cater to them – in real-time
 Monitor players´ profiles to track behavior
changes: target dummy -> veteran
Spatial analytics
 Games are experienced spatio-temporally
 All games require movement
 All games take time to play
 Why is analytics then mainly temporal?
Beyond the heatmap
(Images: Ubisoft,
Microsoft, Square
Enix)
Spatial analytics
 Spatio-temporal analytics
 Does not reduce the dimensions of game metrics data
 Deals with the actual dimensions of play.
(Image: Ubisoft)
Spatial analytics
(Image: Square Enix)
Spatial analytics
 Decades of knowledge in spatial analytics outside
of games – ripe for harvesting
 Trajectory analysis (how do users play the game? Move
in 3D?)
 Spatial outlier detection (finding exploitation spots, bugs)
 Spatial clustering (are players distributed across maps?)
 Spatial co-location patterns/trends (army composition in
RTS)
Adaptive games
 Games that respond to the actions of the user in order to
maximise UX (and/or revenue)
 Left 4 Dead, Borderlands, Terraria, Virus ... – these relatively
primitive but powerful – tip of the iceberg
 Sizeable European/US community of researchers working for a
decade on adaptive games
 Future: Real-Time Analytics driving the game experience, within
pre-planned frame (think pen-and-paper RPGs)
Automatization
 Problem: time consuming analysis and reporting
 Huge potential for automating analysis and reporting,
interactive reports, etc.
 Future: More effective analytics
 Future: More interactive, tailored reports
Diversification
 Currently focus on:
 Player behavior and monetization
 Game analytics is much more:




(Almost) all aspects of a game development can be measured
Integrating and synchronizing data and sources
Do not regulate the creative process!
Games are diversifying! – analytics must follow suit
Knowledge sharing
 Game Analytics – maximizing the value of player data
 50+ experts from industry and research
 2 intro/foundation chapters (on website below):
 Game Analytics: The Basics
 Game Data Mining
 IGDA GUR SIG
 Slides from presentation will be available on: www.andersdrachen.wordpress.com
 Blogs: blog.gameanalytics.com, engineroom.ubi.com, www.gamesbrief.com etc.
 Contact: andersdrachen@gmail.com